About: Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations
Creator	Qi, Peng Hardy, Amelia Kaushik, Ram Kenealy, Kathleen Li, Haojun Manning, Paranjape, Ashwin Phu, Dilara Sadagopan, Nguyet See, Abigail Soylu, Christopher
Source	ArXiv
abstract	We present Chirpy Cardinal, an open-domain dialogue agent, as a research platform for the 2019 Alexa Prize competition. Building an open-domain socialbot that talks to real people is challenging - such a system must meet multiple user expectations such as broad world knowledge, conversational style, and emotional connection. Our socialbot engages users on their terms - prioritizing their interests, feelings and autonomy. As a result, our socialbot provides a responsive, personalized user experience, capable of talking knowledgeably about a wide variety of topics, as well as chatting empathetically about ordinary life. Neural generation plays a key role in achieving these goals, providing the backbone for our conversational and emotional tone. At the end of the competition, Chirpy Cardinal progressed to the finals with an average rating of 3.6/5.0, a median conversation duration of 2 minutes 16 seconds, and a 90th percentile duration of over 12 minutes.
has issue date	2020-08-27(xsd:dateTime)
has license	arxiv
sha1sum (hex)	dde4d0b9a7d59875007f0f142d82934dd2155ef8
resource representing a document's title	Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations
resource representing a document's body	covid:dde4d0b9a7d59875007f0f142d82934dd2155ef8#body_text
is schema:about of	named entity 'emotional' named entity 'Proceedings' named entity 'platform' named entity 'user experience' named entity 'Generation' named entity 'Neural' named entity 'Real People' named entity 'WORLD' named entity 'ROLE' named entity 'WIDE' named entity 'INTERESTS' named entity 'percentile' named entity 'real people' named entity 'lemmatization' named entity 'phoneme' named entity 'Twitter' named entity 'adversarial user' named entity 'binary classification' named entity 'CoBot' named entity 'Wikidata' named entity 'open-domain' named entity 'Wikipedia' named entity 'Microsoft' named entity '5.1' named entity '5.4' named entity 'Washington Post' named entity 'Knowledge Graph' named entity 'regression analysis' named entity 'multinomial logistic regression' named entity 'Frozen 2' named entity 'question mark' named entity 'NLP' named entity 'issue tracking' named entity 'bots' named entity 'statsmodels' named entity 'informs' named entity 'training data' named entity 'Wikipedia' named entity 'language understanding' named entity 'supervised training' named entity 'ASR' named entity 'Figure 8' named entity 'type-checks' named entity 'regular expressions' named entity 'language generation' named entity 'regex' named entity 'Wikipedia' named entity 'statistically significant' named entity 'question answering' named entity 'Wikidata' named entity 'Alexa Prize' named entity 'unigram' named entity 'unigram' named entity 'Automatic Speech Recognition' named entity 'confusion matrix' named entity 'Ice cream' named entity 'API' named entity 'Wikidata' named entity 'bag-of-words' named entity 'socialbot' named entity 'training set' named entity 'test set' named entity 'punctuation' named entity 'Washington Post' named entity 'Coen brothers' named entity '4.2' named entity 'ASR' named entity 'Wiki' named entity 'duration' named entity 'median' named entity 'multiple' named entity 'empathetically' named entity 'progressed' named entity 'Alexa Prize' named entity 'empathetically' named entity 'socialbot' named entity '12 minutes'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software